Fetch prebuilt ONNX from HF for upscale-realplksr instead of converting in CI#33
Closed
andriiryzhkov wants to merge 0 commit into
Closed
Fetch prebuilt ONNX from HF for upscale-realplksr instead of converting in CI#33andriiryzhkov wants to merge 0 commit into
andriiryzhkov wants to merge 0 commit into
Conversation
07d2827 to
4c245a2
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Convert step was hitting noisy-neighbour OOMs on nightly CI. RealPLKSR is the heaviest model we convert (~6 min, peak memory near the GitHub runner's effective limit), and nightly runs at peak infra hours, so the same code that converts fine on PR builds gets the runner killed.
Move conversion out of CI: pre-converted ONNX now live in Hugging Face model repository. CI just downloads the ONNX, the existing validate/package steps run unchanged.